Lists the agents in a location that belong to the caller. An agent belongs to the end user recorded as its owner when it was created, so the response holds that caller's agents and no others. It is empty for a caller that is not an end user, and an agent with no recorded owner is listed for nobody.

Method Details

close()

Close httplib2 connections.

create(parent, body=None, x__xgafv=None)

Creates an agent.

Args:
  parent: string, Required. The resource name of the location to create the agent in. Format: `projects/{project}/locations/{location}`. (required)
  body: object, The request body.
    The object takes the form of:

{ # A Vertex agent contains instructions and configurations for the LLM to execute a certain task.
  "base_agent": "A String", # Required. The base agent for the agent. Supported values: * `antigravity-preview-05-2026`
  "base_environment": "", # Optional. The base environment configuration for the agent. Valid types: * A string value for the environment ID, or `remote` for the default. * A struct value for the `environment_config`.
  "created": "A String", # Output only. The time the agent was created.
  "description": "A String", # Optional. The description of the agent.
  "id": "A String", # Immutable. The user-specified ID for the agent. This ID becomes the final component of the agent resource name. If not provided, Vertex AI will generate a value for this ID. The ID can be up to 63 characters and must match the regular expression `[a-z]([a-z0-9-]{0,61}[a-z0-9])?`.
  "metadata": { # Optional. The metadata for the agent.
    "a_key": "A String",
  },
  "name": "A String", # Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`.
  "object": "A String", # Output only. The object type of the resource. For agents, the value is `agent`.
  "system_instruction": "A String", # Optional. The instructions for the agent to follow. These instructions are passed to the LLM as a system instruction.
  "tools": [ # Optional. The tools available to the agent.
    { # A tool provides a list of actions available to the Agent during the process of executing a task.
      "headers": { # Optional. The headers for the MCP server, such as for authentication. Only applicable when `type` is `mcp_server`.
        "a_key": "A String",
      },
      "name": "A String", # Optional. The name of the MCP server. Only applicable when `type` is `mcp_server`.
      "type": "A String", # Required. The type of the tool. Supported types: * `code_execution` * `filesystem` * `google_search` * `mcp_server` * `url_context`
      "url": "A String", # Optional. The URL for the MCP server endpoint. Only applicable when `type` is `mcp_server`.
    },
  ],
  "updated": "A String", # Output only. The time the agent was last updated.
}

  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # This resource represents a long-running operation that is the result of a network API call.
  "done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
  "error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
    "code": 42, # The status code, which should be an enum value of google.rpc.Code.
    "details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
      {
        "a_key": "", # Properties of the object. Contains field @type with type URL.
      },
    ],
    "message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
  },
  "metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
  "name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
  "response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
    "a_key": "", # Properties of the object. Contains field @type with type URL.
  },
}

delete(name, x__xgafv=None)

Deletes an agent.

Args:
name: string, Required. The resource name of the agent to delete. Format: `projects/{project}/locations/{location}/agents/{agent}`. (required)
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format

Returns:
An object of the form:

{ # This resource represents a long-running operation that is the result of a network API call.
"done": True or False, # If the value is `false`, it means the operation is still in progress. If `true`, the operation is completed, and either `error` or `response` is available.
"error": { # The `Status` type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](https://github.com/grpc). Each `Status` message contains three pieces of data: error code, error message, and error details. You can find out more about this error model and how to work with it in the [API Design Guide](https://cloud.google.com/apis/design/errors). # The error result of the operation in case of failure or cancellation.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There is a common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
"message": "A String", # A developer-facing error message, which should be in English. Any user-facing error message should be localized and sent in the google.rpc.Status.details field, or localized by the client.
},
"metadata": { # Service-specific metadata associated with the operation. It typically contains progress information and common metadata such as create time. Some services might not provide such metadata. Any method that returns a long-running operation should document the metadata type, if any.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
"name": "A String", # The server-assigned name, which is only unique within the same service that originally returns it. If you use the default HTTP mapping, the `name` should be a resource name ending with `operations/{unique_id}`.
"response": { # The normal, successful response of the operation. If the original method returns no data on success, such as `Delete`, the response is `google.protobuf.Empty`. If the original method is standard `Get`/`Create`/`Update`, the response should be the resource. For other methods, the response should have the type `XxxResponse`, where `Xxx` is the original method name. For example, if the original method name is `TakeSnapshot()`, the inferred response type is `TakeSnapshotResponse`.
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
}

get(name, x__xgafv=None)

Retrieves an agent.

Args:
  name: string, Required. The resource name of the agent to retrieve. Format: `projects/{project}/locations/{location}/agents/{agent}`. (required)
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # A Vertex agent contains instructions and configurations for the LLM to execute a certain task.
  "base_agent": "A String", # Required. The base agent for the agent. Supported values: * `antigravity-preview-05-2026`
  "base_environment": "", # Optional. The base environment configuration for the agent. Valid types: * A string value for the environment ID, or `remote` for the default. * A struct value for the `environment_config`.
  "created": "A String", # Output only. The time the agent was created.
  "description": "A String", # Optional. The description of the agent.
  "id": "A String", # Immutable. The user-specified ID for the agent. This ID becomes the final component of the agent resource name. If not provided, Vertex AI will generate a value for this ID. The ID can be up to 63 characters and must match the regular expression `[a-z]([a-z0-9-]{0,61}[a-z0-9])?`.
  "metadata": { # Optional. The metadata for the agent.
    "a_key": "A String",
  },
  "name": "A String", # Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`.
  "object": "A String", # Output only. The object type of the resource. For agents, the value is `agent`.
  "system_instruction": "A String", # Optional. The instructions for the agent to follow. These instructions are passed to the LLM as a system instruction.
  "tools": [ # Optional. The tools available to the agent.
    { # A tool provides a list of actions available to the Agent during the process of executing a task.
      "headers": { # Optional. The headers for the MCP server, such as for authentication. Only applicable when `type` is `mcp_server`.
        "a_key": "A String",
      },
      "name": "A String", # Optional. The name of the MCP server. Only applicable when `type` is `mcp_server`.
      "type": "A String", # Required. The type of the tool. Supported types: * `code_execution` * `filesystem` * `google_search` * `mcp_server` * `url_context`
      "url": "A String", # Optional. The URL for the MCP server endpoint. Only applicable when `type` is `mcp_server`.
    },
  ],
  "updated": "A String", # Output only. The time the agent was last updated.
}

list(parent, orderBy=None, pageSize=None, pageToken=None, x__xgafv=None)

Lists the agents in a location that belong to the caller. An agent belongs to the end user recorded as its owner when it was created, so the response holds that caller's agents and no others. It is empty for a caller that is not an end user, and an agent with no recorded owner is listed for nobody.

Args:
  parent: string, Required. The resource name of the location to list agents from. Format: `projects/{project}/locations/{location}`. (required)
  orderBy: string, Optional. A comma-separated list of fields to order by. Supported fields: * `created` * `updated` Use `desc` after a field name for descending order. Example: `created desc`.
  pageSize: integer, Optional. The maximum number of agents to return. The service may return fewer than this value. The maximum page size is 100; values above 100 will be coerced to 100. If unspecified, the default page size is 10.
  pageToken: string, Optional. A page token, received from a previous AgentService.ListAgents call. Provide this to retrieve the subsequent page.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # Response message for AgentService.ListAgents.
  "agents": [ # The agents matching the request.
    { # A Vertex agent contains instructions and configurations for the LLM to execute a certain task.
      "base_agent": "A String", # Required. The base agent for the agent. Supported values: * `antigravity-preview-05-2026`
      "base_environment": "", # Optional. The base environment configuration for the agent. Valid types: * A string value for the environment ID, or `remote` for the default. * A struct value for the `environment_config`.
      "created": "A String", # Output only. The time the agent was created.
      "description": "A String", # Optional. The description of the agent.
      "id": "A String", # Immutable. The user-specified ID for the agent. This ID becomes the final component of the agent resource name. If not provided, Vertex AI will generate a value for this ID. The ID can be up to 63 characters and must match the regular expression `[a-z]([a-z0-9-]{0,61}[a-z0-9])?`.
      "metadata": { # Optional. The metadata for the agent.
        "a_key": "A String",
      },
      "name": "A String", # Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`.
      "object": "A String", # Output only. The object type of the resource. For agents, the value is `agent`.
      "system_instruction": "A String", # Optional. The instructions for the agent to follow. These instructions are passed to the LLM as a system instruction.
      "tools": [ # Optional. The tools available to the agent.
        { # A tool provides a list of actions available to the Agent during the process of executing a task.
          "headers": { # Optional. The headers for the MCP server, such as for authentication. Only applicable when `type` is `mcp_server`.
            "a_key": "A String",
          },
          "name": "A String", # Optional. The name of the MCP server. Only applicable when `type` is `mcp_server`.
          "type": "A String", # Required. The type of the tool. Supported types: * `code_execution` * `filesystem` * `google_search` * `mcp_server` * `url_context`
          "url": "A String", # Optional. The URL for the MCP server endpoint. Only applicable when `type` is `mcp_server`.
        },
      ],
      "updated": "A String", # Output only. The time the agent was last updated.
    },
  ],
  "nextPageToken": "A String", # A token to retrieve the next page of results. Pass this value as ListAgentsRequest.page_token in a subsequent call.
}

list_next()

Retrieves the next page of results.

        Args:
          previous_request: The request for the previous page. (required)
          previous_response: The response from the request for the previous page. (required)

        Returns:
          A request object that you can call 'execute()' on to request the next
          page. Returns None if there are no more items in the collection.

patch(name, body=None, updateMask=None, x__xgafv=None)

Updates an agent.

Args:
  name: string, Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`. (required)
  body: object, The request body.
    The object takes the form of:

{ # A Vertex agent contains instructions and configurations for the LLM to execute a certain task.
  "base_agent": "A String", # Required. The base agent for the agent. Supported values: * `antigravity-preview-05-2026`
  "base_environment": "", # Optional. The base environment configuration for the agent. Valid types: * A string value for the environment ID, or `remote` for the default. * A struct value for the `environment_config`.
  "created": "A String", # Output only. The time the agent was created.
  "description": "A String", # Optional. The description of the agent.
  "id": "A String", # Immutable. The user-specified ID for the agent. This ID becomes the final component of the agent resource name. If not provided, Vertex AI will generate a value for this ID. The ID can be up to 63 characters and must match the regular expression `[a-z]([a-z0-9-]{0,61}[a-z0-9])?`.
  "metadata": { # Optional. The metadata for the agent.
    "a_key": "A String",
  },
  "name": "A String", # Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`.
  "object": "A String", # Output only. The object type of the resource. For agents, the value is `agent`.
  "system_instruction": "A String", # Optional. The instructions for the agent to follow. These instructions are passed to the LLM as a system instruction.
  "tools": [ # Optional. The tools available to the agent.
    { # A tool provides a list of actions available to the Agent during the process of executing a task.
      "headers": { # Optional. The headers for the MCP server, such as for authentication. Only applicable when `type` is `mcp_server`.
        "a_key": "A String",
      },
      "name": "A String", # Optional. The name of the MCP server. Only applicable when `type` is `mcp_server`.
      "type": "A String", # Required. The type of the tool. Supported types: * `code_execution` * `filesystem` * `google_search` * `mcp_server` * `url_context`
      "url": "A String", # Optional. The URL for the MCP server endpoint. Only applicable when `type` is `mcp_server`.
    },
  ],
  "updated": "A String", # Output only. The time the agent was last updated.
}

  updateMask: string, Optional. The list of fields to update. If not present, all fields are updated.
  x__xgafv: string, V1 error format.
    Allowed values
      1 - v1 error format
      2 - v2 error format

Returns:
  An object of the form:

    { # A Vertex agent contains instructions and configurations for the LLM to execute a certain task.
  "base_agent": "A String", # Required. The base agent for the agent. Supported values: * `antigravity-preview-05-2026`
  "base_environment": "", # Optional. The base environment configuration for the agent. Valid types: * A string value for the environment ID, or `remote` for the default. * A struct value for the `environment_config`.
  "created": "A String", # Output only. The time the agent was created.
  "description": "A String", # Optional. The description of the agent.
  "id": "A String", # Immutable. The user-specified ID for the agent. This ID becomes the final component of the agent resource name. If not provided, Vertex AI will generate a value for this ID. The ID can be up to 63 characters and must match the regular expression `[a-z]([a-z0-9-]{0,61}[a-z0-9])?`.
  "metadata": { # Optional. The metadata for the agent.
    "a_key": "A String",
  },
  "name": "A String", # Identifier. The resource name of the agent. Format: `projects/{project}/locations/{location}/agents/{agent}`.
  "object": "A String", # Output only. The object type of the resource. For agents, the value is `agent`.
  "system_instruction": "A String", # Optional. The instructions for the agent to follow. These instructions are passed to the LLM as a system instruction.
  "tools": [ # Optional. The tools available to the agent.
    { # A tool provides a list of actions available to the Agent during the process of executing a task.
      "headers": { # Optional. The headers for the MCP server, such as for authentication. Only applicable when `type` is `mcp_server`.
        "a_key": "A String",
      },
      "name": "A String", # Optional. The name of the MCP server. Only applicable when `type` is `mcp_server`.
      "type": "A String", # Required. The type of the tool. Supported types: * `code_execution` * `filesystem` * `google_search` * `mcp_server` * `url_context`
      "url": "A String", # Optional. The URL for the MCP server endpoint. Only applicable when `type` is `mcp_server`.
    },
  ],
  "updated": "A String", # Output only. The time the agent was last updated.
}

Agent Platform API . projects . locations . agents

Instance Methods

Method Details